dsh.so
EN
English中文
deepseek-harness-meida avatar

deepseek-harness-meida

use glm/minimax/openai/claude api in your deepseek harness

PluginAI ModelsNetwork
Verification
L1 · Found
Security
Medium
Health
Active
Trust
Unrated

What it doesAI

Enables using GLM, MiniMax, OpenAI, and Claude APIs inside the DeepSeek harness.

  • Support for GLM, MiniMax, OpenAI, Claude APIs
  • Dynamic plugin or formal npm install
  • No changes to DeepSeek harness source

AI-generated from the repo README — for reference only.

Installation

dsh plugin --profile web add github:lo2589/deepseek-harness-meida

Install method: GitHub · not yet tested in container (L3+)

Compatibility

DSH VersionStatus
not statedDeclared — not tested

Requirements

  • • Node.js: not stated
  • • DSH: declared "not stated"
  • • External credentials: none detected

Security Report

Automated static scan, not manual review.

DSH.SO AUDITMEDIUMb4ddfa
Security reviewAutomated review · daily
MEDIUM

Critical findings in non-blocking categories (dynamic code execution, shell execution, install scripts, obfuscation). Common in CLI/terminal plugins but worth reviewing.

3 critical·2 warning·8 info·4 files scanned
code-exec ×3
Version binding
plugin version—
scanned commitb4ddfaec4cd22026-08-20
latest commitb4ddfaec4cd2

The scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Second-opinion scan (vet · parallel evaluation)
vet: suspicious

vet verdict: vet: suspicious · score 0

  • R9 · info [heuristic] — 无出口常驻循环（含 await，可能是合法服务循环；交由 LLM 审计复核上下文）
  • R2 · medium [likely] — require('node:fs') 标准内置模块
  • R2 · medium [likely] — require('node:fs') 标准内置模块
  • R2 · medium [likely] — require('node:path') 标准内置模块
  • R2 · medium [likely] — require('node:fs') 标准内置模块

vet is advisory and does not change dsh’s four-tier level.

Risk: Medium3 critical · 2 warning · 8 info

• Static heuristic scan: done (4 files)

• Dependency vulnerabilities: requires deep audit (L3+)

• Permission sandboxing: requires runtime testing (L4+)

High-risk findings · 5 / 5

  • criticalChild process module usage (Node.js)dsh-provider-quick-config/src/host.js:902
    let childProcess
  • criticalChild process module usage (Node.js)dsh-provider-quick-config/src/host.js:903
    try { childProcess = require('node:child_process') } catch (e) { childProcess = undefined }
  • criticalChild process module usage (Node.js)dsh-provider-quick-config/src/host.js:904
    if (childProcess === undefined) {
  • warningHTTP request to a raw IP addressdsh-provider-quick-config/src/client.js:194
    api: 'openai-completions', baseURL: 'http://127.0.0.1:8080/v1',
  • warningHTTP request to a raw IP addressdsh-provider-quick-config/src/client.js:274
    { key: 'mlx', displayName: '本地模型 (MLX)', baseURL: 'http://127.0.0.1:8080/v1' },

Heuristic static scan — may produce false positives. Review the source yourself before trusting.

Activity

Last commit 2026-08-19 · activity: Active

• Repo created: 2026-08-20

• Stars: ★ 4 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/lo2589/deepseek-harness-meida

Was this page helpful?